Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 274 761 563 488 584 391 462 476 920 352 741 932 579 730 411 401 678 925 431 501
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 462  NA 678 925 741 391 501 563  NA  NA 584 411 579 920 932 488 476 401 274 730 761 431 352
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 2 1 4 2 4 3 3 4 1
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y"
[26] "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y"
[26] "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "h" "p" "o" "n" "s" "B" "X" "D" "U" "E"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  9 12 18
which( manyNumbersWithNA > 900 )
[1]  4 14 15
which( is.na( manyNumbersWithNA ) )
[1]  2  9 10

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 920 932 925
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 920 932 925
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 920 932 925

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "B" "X" "D" "U" "E"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "h" "p" "o" "n" "s"
manyNumbers %in% 300:600
 [1] FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE  TRUE FALSE FALSE  TRUE FALSE  TRUE  TRUE
[17] FALSE FALSE  TRUE  TRUE
which( manyNumbers %in% 300:600 )
 [1]  3  4  5  6  7  8 10 13 15 16 19 20
sum( manyNumbers %in% 300:600 )
[1] 12

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" NA      "large" "large" "large" "small" "large" "large" NA      NA      "large" "small"
[13] "large" "large" "large" "small" "small" "small" "small" "large" "large" "small" "small"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "UNKNOWN" "large"   "large"   "large"   "small"   "large"   "large"   "UNKNOWN" "UNKNOWN"
[11] "large"   "small"   "large"   "large"   "large"   "small"   "small"   "small"   "small"   "large"  
[21] "large"   "small"   "small"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0  NA 678 925 741   0 501 563  NA  NA 584   0 579 920 932   0   0   0   0 730 761   0   0

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 2 4 3
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  2  4  3
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 15
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 932
which.min( manyNumbersWithNA )
[1] 19
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 274
range( manyNumbersWithNA, na.rm = TRUE )
[1] 274 932

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 462  NA 678 925 741 391 501 563  NA  NA 584 411 579 920 932 488 476 401 274 730 761 431 352
sort( manyNumbersWithNA )
 [1] 274 352 391 401 411 431 462 476 488 501 563 579 584 678 730 741 761 920 925 932
sort( manyNumbersWithNA, na.last = TRUE )
 [1] 274 352 391 401 411 431 462 476 488 501 563 579 584 678 730 741 761 920 925 932  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 932 925 920 761 741 730 678 584 579 563 501 488 476 462 431 411 401 391 352 274  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 462  NA 678 925 741
order( manyNumbersWithNA[1:5] )
[1] 1 3 5 4 2
rank( manyNumbersWithNA[1:5] )
[1] 1 5 2 4 3
sort( mixedLetters )
 [1] "B" "D" "E" "h" "n" "o" "p" "s" "U" "X"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  3.0  6.0  6.0 10.0  1.0  3.0  3.0  8.5  8.5  6.0
rank( manyDuplicates, ties.method = "min" )
 [1]  2  5  5 10  1  2  2  8  8  5
rank( manyDuplicates, ties.method = "random" )
 [1]  4  7  6 10  1  2  3  8  9  5

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000  0.70627580 -1.01876508 -1.51830294
 [9] -0.09008336 -0.49251081  0.69435234 -0.50235180 -1.06037165 -0.33586753 -1.03670333
round( v, 0 )
 [1] -1  0  0  0  1  1 -1 -2  0  0  1 -1 -1  0 -1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.7 -1.0 -1.5 -0.1 -0.5  0.7 -0.5 -1.1 -0.3 -1.0
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.71 -1.02 -1.52 -0.09 -0.49  0.69 -0.50 -1.06 -0.34 -1.04
floor( v )
 [1] -1 -1  0  0  1  0 -2 -2 -1 -1  0 -1 -2 -1 -2
ceiling( v )
 [1] -1  0  0  1  1  1 -1 -1  0  0  1  0 -1  0 -1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2023 Biomedical Data Sciences (BDS) | LUMC